AI Infrastructure: Technical Integration Testing
How do we ensure what we built actually works in production?
My name is Erkin Ötleş & I’m a physician-engineer. This unique combination of roles allows me to bridge the gap between medicine and engineering, a perspective I bring to my work in AI for medicine.
I am currently an emergency medicine resident physician at the University of Wisconsin. I previously was a Medical Scientist Training Program Fellow at the University of Michigan; I got a combined MD-PhD (doctorates in medicine & engineering). Before that, I worked as an engineer focused on solving healthcare data problems; I spent some time at Epic and also led a healthcare data science team. I am an expert in developing & implementing artificial intelligence tools in healthcare, such as predictive analytics for patient outcomes and machine learning algorithms for disease recognition.
All models are wrong, but some are useful.
- George Box -
How do we ensure what we built actually works in production?
Discussion of the technical integration for an in-hospital infection risk stratification model.
Infrastructure is king.
A detailed exploration of the development and implementation of M-CURES, a COVID-19 in-hospital deterioration model, highlighting the integration of AI model...
A guide to the technical infrastructure needed to integrate AI models into clinical workflows, covering both internal and external integration approaches and...
Medicine is a science of uncertainty and an art of probability.
- William Osler -